Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Signal Processing Letters Année : 2024

Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering

Résumé

The performance of spectral clustering relies on the fluctuations of the entries of the eigenvectors of a similarity matrix, which has been left uncharacterized until now. In this letter, it is shown that the signal + noise structure of a general spike random matrix model is transferred to the eigenvectors of the corresponding Gram kernel matrix and the fluctuations of their entries are Gaussian in the large-dimensional regime. This CLT-like result was the last missing piece to precisely predict the classification performance of spectral clustering. The proposed proof is very general and relies solely on the rotational invariance of the noise. Numerical experiments on synthetic and real data illustrate the universality of this phenomenon.
Fichier principal
Vignette du fichier
2402.12302v2.pdf (734.77 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04673319 , version 1 (20-08-2024)

Licence

Identifiants

Citer

Hugo Lebeau, Florent Chatelain, Romain Couillet. Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering. IEEE Signal Processing Letters, 2024, 31, pp.1920-1924. ⟨10.1109/LSP.2024.3422886⟩. ⟨hal-04673319⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More